这是我能想到的最好的算法。
def get_primes(n):
numbers = set(range(n, 1, -1))
primes = []
while numbers:
p = numbers.pop()
primes.append(p)
numbers.difference_update(set(range(p*2, n+1, p)))
return primes
>>> timeit.Timer(stmt='get_primes.get_primes(1000000)', setup='import get_primes').timeit(1)
1.1499958793645562
还能做得更快吗?
这段代码有一个缺陷:由于numbers是一个无序集,不能保证numbers.pop()将从集合中移除最低的数字。尽管如此,它还是适用于(至少对我来说)一些输入数字:
>>> sum(get_primes(2000000))
142913828922L
#That's the correct sum of all numbers below 2 million
>>> 529 in get_primes(1000)
False
>>> 529 in get_primes(530)
True
这里是最快的函数之一的两个更新版本(纯Python 3.6),
from itertools import compress
def rwh_primes1v1(n):
""" Returns a list of primes < n for n > 2 """
sieve = bytearray([True]) * (n//2)
for i in range(3,int(n**0.5)+1,2):
if sieve[i//2]:
sieve[i*i//2::i] = bytearray((n-i*i-1)//(2*i)+1)
return [2,*compress(range(3,n,2), sieve[1:])]
def rwh_primes1v2(n):
""" Returns a list of primes < n for n > 2 """
sieve = bytearray([True]) * (n//2+1)
for i in range(1,int(n**0.5)//2+1):
if sieve[i]:
sieve[2*i*(i+1)::2*i+1] = bytearray((n//2-2*i*(i+1))//(2*i+1)+1)
return [2,*compress(range(3,n,2), sieve[1:])]
使用Numpy实现的半筛子略有不同:
http://rebrained.com/?p=458
import math
import numpy
def prime6(upto):
primes=numpy.arange(3,upto+1,2)
isprime=numpy.ones((upto-1)/2,dtype=bool)
for factor in primes[:int(math.sqrt(upto))]:
if isprime[(factor-2)/2]: isprime[(factor*3-2)/2:(upto-1)/2:factor]=0
return numpy.insert(primes[isprime],0,2)
有人能把这个和其他时间比较一下吗?在我的机器上,它似乎与其他Numpy半筛相当。
随着时间的推移,我收集了几个质数筛子。我电脑上最快的是这样的:
from time import time
# 175 ms for all the primes up to the value 10**6
def primes_sieve(limit):
a = [True] * limit
a[0] = a[1] = False
#a[2] = True
for n in xrange(4, limit, 2):
a[n] = False
root_limit = int(limit**.5)+1
for i in xrange(3,root_limit):
if a[i]:
for n in xrange(i*i, limit, 2*i):
a[n] = False
return a
LIMIT = 10**6
s=time()
primes = primes_sieve(LIMIT)
print time()-s
对于最快的代码,numpy解决方案是最好的。不过,出于纯粹的学术原因,我发布了我的纯python版本,它比上面发布的食谱版本快不到50%。由于我将整个列表放在内存中,所以需要足够的空间来容纳所有内容,但它的可伸缩性似乎相当好。
def daniel_sieve_2(maxNumber):
"""
Given a number, returns all numbers less than or equal to
that number which are prime.
"""
allNumbers = range(3, maxNumber+1, 2)
for mIndex, number in enumerate(xrange(3, maxNumber+1, 2)):
if allNumbers[mIndex] == 0:
continue
# now set all multiples to 0
for index in xrange(mIndex+number, (maxNumber-3)/2+1, number):
allNumbers[index] = 0
return [2] + filter(lambda n: n!=0, allNumbers)
结果是:
>>>mine = timeit.Timer("daniel_sieve_2(1000000)",
... "from sieves import daniel_sieve_2")
>>>prev = timeit.Timer("get_primes_erat(1000000)",
... "from sieves import get_primes_erat")
>>>print "Mine: {0:0.4f} ms".format(min(mine.repeat(3, 1))*1000)
Mine: 428.9446 ms
>>>print "Previous Best {0:0.4f} ms".format(min(prev.repeat(3, 1))*1000)
Previous Best 621.3581 ms
如果你接受itertools,但不接受numpy,这里有一个针对Python 3的rwh_primes2的改编版本,它在我的机器上运行速度大约是原来的两倍。唯一的实质性变化是使用bytearray而不是列表来表示布尔值,并使用压缩而不是列表推导来构建最终列表。(如果可以的话,我会把这句话作为moarningsun之类的评论。)
import itertools
izip = itertools.zip_longest
chain = itertools.chain.from_iterable
compress = itertools.compress
def rwh_primes2_python3(n):
""" Input n>=6, Returns a list of primes, 2 <= p < n """
zero = bytearray([False])
size = n//3 + (n % 6 == 2)
sieve = bytearray([True]) * size
sieve[0] = False
for i in range(int(n**0.5)//3+1):
if sieve[i]:
k=3*i+1|1
start = (k*k+4*k-2*k*(i&1))//3
sieve[(k*k)//3::2*k]=zero*((size - (k*k)//3 - 1) // (2 * k) + 1)
sieve[ start ::2*k]=zero*((size - start - 1) // (2 * k) + 1)
ans = [2,3]
poss = chain(izip(*[range(i, n, 6) for i in (1,5)]))
ans.extend(compress(poss, sieve))
return ans
比较:
>>> timeit.timeit('primes.rwh_primes2(10**6)', setup='import primes', number=1)
0.0652179726976101
>>> timeit.timeit('primes.rwh_primes2_python3(10**6)', setup='import primes', number=1)
0.03267321276325674
and
>>> timeit.timeit('primes.rwh_primes2(10**8)', setup='import primes', number=1)
6.394284538007014
>>> timeit.timeit('primes.rwh_primes2_python3(10**8)', setup='import primes', number=1)
3.833829450302801